Enrichment
Turn legal documents into hallucination-free knowledge graphs
Overview
Legal documents, made machine-readable.
Enrichment transforms unstructured legal documents into rich, structured, hierarchical knowledge graphs. Use it to capture sections, concepts, entities, citations, and relationships so your product can work with legal documents as data, not just text.
Why it matters
Structure your documents before you build on them
Kanon 2 Enricher gives legal engineers and product builders a graph-native, hallucination-free way to understand long, complex legal materials.
-
Turn documents into graphs
Transform unstructured legal documents of any length into rich, structured knowledge graphs that capture sections, concepts, entities, citations, and the relationships between them.
-
Beyond extraction
Kanon 2 Enricher does not just extract entities. It disambiguates them, links them together, and fully deconstructs the structural hierarchy of legal documents.
-
Hallucination-free by design
Because Kanon 2 Enricher natively outputs knowledge graphs rather than tokens, it is architecturally incapable of producing the hallucinations suffered by general-purpose generative models.
How teams use it
From raw documents to reusable legal data
Power document intelligence, search, analytics, automation, and agentic workflows with structured legal knowledge graphs.
Knowledge graphs for legal documents
Convert legal text into structured data that applications can search, traverse, validate, and reason over.
Legal documents are full of structure: headings, clauses, definitions, parties, citations, dates, obligations, exceptions, remedies, and relationships that matter. Enrichment turns that hidden structure into a graph your product can use.
Instead of treating a document as a flat block of text, Kanon 2 Enricher maps its hierarchy and links the important concepts and entities inside it. That gives legal engineers a richer substrate for search, review, analytics, automation, and agentic workflows.
For vibe coders, the value is immediate: upload a document, get back structured legal data, and build features that would be painful to create from raw text alone.
Kanon 2 Enricher
A hierarchical graphitization model that turns unstructured legal documents into rich, structured knowledge graphs.
Kanon 2 Enricher belongs to an entirely new class of AI models known as hierarchical graphitization models. It transforms unstructured documents of any length into rich, highly structured knowledge graphs with sub-second latency.
Unlike universal extraction models such as GLiNER2, Kanon 2 Enricher can not only extract entities referenced within documents but can also disambiguate entities and link them together, as well as fully deconstruct the structural hierarchy of documents.
Because it natively outputs knowledge graphs rather than tokens, Kanon 2 Enricher is architecturally incapable of producing the types of hallucinations suffered by general-purpose generative models. Its graph-first architecture is small enough to run locally on a consumer PC while still outperforming frontier LLMs like Gemini 3.1 Pro and GPT-5.2.
Hallucination-free legal workflows
Use enrichment when your product needs structured legal facts and relationships, not generated prose.
Many legal AI systems ask a language model to infer structure every time they run. Enrichment moves that work upstream by converting documents into a reusable graph that can be inspected, stored, queried, and connected to the rest of your stack.
Kanon 2 Enricher is hallucination-free by design. Because it produces structured graph outputs rather than free-form tokens, it cannot invent prose, citations, entities, or relationships in the way general-purpose generative models can.
Use enriched graphs to build document intelligence tools, knowledge bases, contract analysis systems, litigation workflows, regulatory maps, citation networks, and applications that need to understand how legal documents are put together.